Mythos-Nexus beta is live for $MYTHOS holders - Nexus beta - Try it out

███╗ ███╗██╗ ██╗████████╗██╗ ██╗ ██████╗ ███████╗ ████╗ ████║╚██╗ ██╔╝╚══██╔══╝██║ ██║██╔═══██╗██╔════╝ ██╔████╔██║ ╚████╔╝ ██║ ███████║██║ ██║███████╗ ██║╚██╔╝██║ ╚██╔╝ ██║ ██╔══██║██║ ██║╚════██║ ██║ ╚═╝ ██║ ██║ ██║ ██║ ██║╚██████╔╝███████║ ╚═╝ ╚═╝ ╚═╝ ╚═╝ ╚═╝ ╚═╝ ╚═════╝ ╚══════╝

Stop AI from lying about your code.

The local CLI that forces AI agents to prove their file edits against your actual filesystem. Zero slop. Full verification.

$ npx mythos-router chatCopied
GitHub
CA: 0xb942b75a602fa318ac091370d93d9143ba345ba3Copied
Claude Opus 4.7Strict Write DisciplineMIT License
mythos-router — chat

Choose the path that matches your setup

Start with the path you actually need. Mythos can run the agent, load repo rules, or act as the verified file-edit boundary for another agent.


The part worth showing is the proof layer.

Mythos does not ask you to trust a model's story. It treats each file edit as a claim, compares it with the real filesystem, and records what actually happened.

A normal edit finishes with filesystem proof.

The model proposes file actions, SWD checks the actual disk state, and the run only completes after the edit matches the claim.

mythos-router — run
~ ❯ mythos run --file TASK.md~ ❯ mythos run --file TASK.md
  
┌─ Session ──────────────────────────────────────────────┐Session
│ Provider auto │Provider: auto
│ Model claude-opus-4-7 │Model: claude-opus-4-7
│ Mode dry-run: off · budget: on │Mode: dry-run off · budget on
│ Branch main │Branch: main
│ Memory 42 entries · status: active │Memory: 42 entries · active
│ Budget 0 / 500k tokens · 0 / 3 turns │Budget: 0/500k tokens · 0/3 turns
└────────────────────────────────────────────────────────┘────────────────────────
────────────────────────────────────────────────────────────────────────────────────
✔ Reasoning complete✔ Reasoning complete
Updating the v1.9.0 usage docs from TASK.md.Updating the v1.9.0 usage docs from TASK.md.
  
── SWD Verification ──── SWD Verification ──
✔ Verified: MODIFY README.md ✔ Verified: MODIFY README.md
✔ Verified: MODIFY CHANGELOG.md ✔ Verified: MODIFY CHANGELOG.md
Receipt: mythos receipts show swd_2026_05_20_19f4c2Receipt: swd_2026_05_20_19f4c2
  
Tokens: 3,204 in · 1,608 out · 4,812 total via anthropic/claude-opus-4-7Tokens: 4,812 total via anthropic
Budget: [░░░░░░░░░░░░░░░░░░░░] 4,812/500,000 tokens · [███░░░░░░░] 1/3 turns · ~$0.0241 · 4sBudget: 4,812/500k · 1/3 turns · ~$0.0241 · 4s
  
Run completeRun complete
Duration: 4s | Turns: 1/3 | Tokens: 4,812/500,000 | Cost: ~$0.0241 | Memory entries: +1Duration: 4s · Turns: 1/3 · Memory +1
ClaimMODIFY README.md and CHANGELOG.md
Checkhash, intent, and disk state matched
Outcomereceipt created

Static playback using the current CLI output shape.


Built for verifiable agent work

Mythos Router is not another chat wrapper. It is a local execution boundary for model output, repo rules, receipts, MCP clients, and external-agent file actions.

Strict Write Discipline

Every claimed file edit is checked against the real filesystem with before and after snapshots, hashes, and verification status.

MCP adapter for SWD

MCP clients can use mythos mcp as a local tool server for dry-runs, verified applies, receipts, and skill inspection.

One-shot run mode

Use mythos run for scriptable one-off tasks from inline prompts, files, or stdin while keeping the same SWD, memory, budget, skills, and receipt path.

Repo skills

Keep project rules in .mythos/skills/<name>/SKILL.md or personal reusable rules in ~/.mythos-router/skills. Active skills are recorded in receipts.

Repo learning

mythos learn creates a reviewable repo-local SKILL.md from local project signals without running npm scripts, tests, builds, or model calls.

Receipts and drift checks

Verified runs write local receipts with file hashes, provider or external-agent metadata, git context, rollback status, and later drift verification.


One verified path for agent writes

Mythos can be the agent interface or just the execution layer. The trust model stays the same either way.

1

Model or agent proposes actions

Use Mythos chat/run, or bring your own external agent through mythos mcp or mythos swd apply.

-
2

Mythos validates the boundary

Input is parsed, paths are constrained to the project, sensitive files are blocked, and high-impact actions require explicit opt-in.

-
3

SWD applies and verifies

The engine snapshots disk state, applies approved changes, verifies the actual filesystem, and rolls back failed writes.

-
4

Receipts keep the record

Successful non-dry-run writes produce local receipts with file hashes, provider, MCP, or external-agent metadata, git context, and drift checks.


Copy the command you need

Install Mythos locally, then run the command for your flow. Chat and run need a provider key; MCP and external-agent SWD can verify submitted file actions without a Mythos model call.

Install globally
$ npm install -g mythos-router
Interactive chat
$ mythos chat
One-shot task
$ mythos run --file TASK.md
MCP tool server
$ mythos mcp
Read-only setup check
$ mythos init --check

Live on Base

$MYTHOS

The native token for the mythos-router ecosystem on Base. API billing integrations and token-gated features are on the roadmap — building the core engine first.

Live Market Datavia DexScreener ↗
Price
24h Change
Market Cap
24h Volume
Liquidity
24h Txns
CA:0xb942b75a602fa318ac091370d93d9143ba345ba3
Basescan ↗Trade on Uniswap ↗